Search Results for author: Hedvig Kjellstrom

Found 9 papers, 0 papers with code

Causal discovery from conditionally stationary time-series

no code implementations12 Oct 2021 Carles Balsells Rodas, Ruibo Tu, Hedvig Kjellstrom

Causal discovery, i. e., inferring underlying cause-effect relationships from observations of a scene or system, is an inherent mechanism in human cognition, but has been shown to be highly challenging to automate.

Causal Discovery Causal Inference +3

Learn the Time to Learn: Replay Scheduling for Continual Learning

no code implementations29 Sep 2021 Marcus Klasson, Hedvig Kjellstrom, Cheng Zhang

Inspired by human learning, we illustrate that scheduling over which tasks to revisit is critical to the final performance with finite memory resources.

Continual Learning Scheduling

Advances in Variational Inference

no code implementations15 Nov 2017 Cheng Zhang, Judith Butepage, Hedvig Kjellstrom, Stephan Mandt

Many modern unsupervised or semi-supervised machine learning algorithms rely on Bayesian probabilistic models.

Variational Inference

Machine Learning and Social Robotics for Detecting Early Signs of Dementia

no code implementations5 Sep 2017 Patrik Jonell, Joseph Mendelson, Thomas Storskog, Goran Hagman, Per Ostberg, Iolanda Leite, Taras Kucherenko, Olga Mikheeva, Ulrika Akenine, Vesna Jelic, Alina Solomon, Jonas Beskow, Joakim Gustafson, Miia Kivipelto, Hedvig Kjellstrom

This paper presents the EACare project, an ambitious multi-disciplinary collaboration with the aim to develop an embodied system, capable of carrying out neuropsychological tests to detect early signs of dementia, e. g., due to Alzheimer's disease.

BIG-bench Machine Learning

Determinantal Point Processes for Mini-Batch Diversification

no code implementations1 May 2017 Cheng Zhang, Hedvig Kjellstrom, Stephan Mandt

The DPP relies on a similarity measure between data points and gives low probabilities to mini-batches which contain redundant data, and higher probabilities to mini-batches with more diverse data.

Point Processes

Diagnostic Prediction Using Discomfort Drawings

no code implementations5 Dec 2016 Cheng Zhang, Hedvig Kjellstrom, Bo C. Bertilson

In this paper, we explore the possibility to apply machine learning to make diagnostic predictions using discomfort drawings.

BIG-bench Machine Learning

Diagnostic Prediction Using Discomfort Drawings with IBTM

no code implementations27 Jul 2016 Cheng Zhang, Hedvig Kjellstrom, Carl Henrik Ek, Bo C. Bertilson

The positive result indicates a significant potential of machine learning to be used for parts of the pain diagnostic process and to be a decision support system for physicians and other health care personnel.

BIG-bench Machine Learning Clustering

Inter-Battery Topic Representation Learning

no code implementations19 May 2016 Cheng Zhang, Hedvig Kjellstrom, Carl Henrik Ek

The structured representation leads to a model that marries benefits traditionally associated with a discriminative approach, such as feature selection, with those of a generative model, such as principled regularization and ability to handle missing data.

feature selection Representation Learning +1

Factorized Topic Models

no code implementations15 Jan 2013 Cheng Zhang, Carl Henrik Ek, Andreas Damianou, Hedvig Kjellstrom

In this paper we present a modification to a latent topic model, which makes the model exploit supervision to produce a factorized representation of the observed data.

General Classification Topic Models +1

Cannot find the paper you are looking for? You can Submit a new open access paper.